Docx Manipulation

by claude-office-skills9c4c7d5cd281MIT499 starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated 8 months ago

Create, edit, and manipulate Word documents programmatically using python-docx

Instructions onlyDocuments & Office

AI-generated overview

Creates, edits, and manipulates Word .docx documents programmatically using the python-docx library.

What it does: This skill guides an agent in generating python-docx code to build and modify Microsoft Word documents. It covers document creation, headings, paragraphs, tables, images, styles, page setup, headers and footers, and template placeholder filling. It produces .docx files such as reports, letters, and contracts.
When to use it: Use it when a Word document must be generated or edited programmatically, such as producing a formatted report, business letter, or contract from content or data. It also fits filling template placeholders and merging or extracting text from .docx files.
Requirements: Requires the python-docx package and a Python runtime to execute the generated code. The skill itself ships no scripts; it is instructions only. Some listed capabilities reference an office-mcp server with tools such as create_docx and merge_docx_files.

DOCX Manipulation Skill

Overview

This skill enables programmatic creation, editing, and manipulation of Microsoft Word (.docx) documents using the python-docx library. Create professional documents with proper formatting, styles, tables, and images without manual editing.

How to Use

Describe what you want to create or modify in a Word document
Provide any source content (text, data, images)
I'll generate python-docx code and execute it

Example prompts:

"Create a professional report with title, headings, and a table"
"Add a header and footer to this document"
"Generate a contract document with placeholders"
"Convert this markdown content to a styled Word document"

Domain Knowledge

python-docx Fundamentals

python

from docx import Documentfrom docx.shared import Inches, Pt, Cmfrom docx.enum.text import WD_ALIGN_PARAGRAPHfrom docx.enum.style import WD_STYLE_TYPE
# Create new documentdoc = Document()
# Or open existingdoc = Document('existing.docx')

from docx import Documentfrom docx.shared import Inches, Pt, Cmfrom docx.enum.text import WD_ALIGN_PARAGRAPHfrom docx.enum.style import WD_STYLE_TYPE
# Create new documentdoc = Document()
# Or open existingdoc = Document('existing.docx')

Document Structure

Document├── sections (margins, orientation, size)├── paragraphs (text with formatting)├── tables (rows, cells, merged cells)├── pictures (inline images)└── styles (predefined formatting)

Document├── sections (margins, orientation, size)├── paragraphs (text with formatting)├── tables (rows, cells, merged cells)├── pictures (inline images)└── styles (predefined formatting)

Adding Content

Paragraphs & Headings

python

# Add heading (level 0-9)doc.add_heading('Main Title', level=0)doc.add_heading('Section Title', level=1)
# Add paragraphpara = doc.add_paragraph('Normal text here')
# Add styled paragraphdoc.add_paragraph('Note: Important!', style='Intense Quote')
# Add with inline formattingpara = doc.add_paragraph()para.add_run('Bold text').bold = Truepara.add_run(' and ')para.add_run('italic text').italic = True

# Add heading (level 0-9)doc.add_heading('Main Title', level=0)doc.add_heading('Section Title', level=1)
# Add paragraphpara = doc.add_paragraph('Normal text here')
# Add styled paragraphdoc.add_paragraph('Note: Important!', style='Intense Quote')
# Add with inline formattingpara = doc.add_paragraph()para.add_run('Bold text').bold = Truepara.add_run(' and ')para.add_run('italic text').italic = True

Tables

python

# Create tabletable = doc.add_table(rows=3, cols=3)table.style = 'Table Grid'
# Add contenttable.cell(0, 0).text = 'Header 1'table.rows[0].cells[1].text = 'Header 2'
# Add row dynamicallyrow = table.add_row()row.cells[0].text = 'New data'
# Merge cellsa = table.cell(0, 0)b = table.cell(0, 2)a.merge(b)

# Create tabletable = doc.add_table(rows=3, cols=3)table.style = 'Table Grid'
# Add contenttable.cell(0, 0).text = 'Header 1'table.rows[0].cells[1].text = 'Header 2'
# Add row dynamicallyrow = table.add_row()row.cells[0].text = 'New data'
# Merge cellsa = table.cell(0, 0)b = table.cell(0, 2)a.merge(b)

Images

python

# Add image with sizedoc.add_picture('image.png', width=Inches(4))
# Add to specific paragraphpara = doc.add_paragraph()run = para.add_run()run.add_picture('logo.png', width=Inches(1.5))

# Add image with sizedoc.add_picture('image.png', width=Inches(4))
# Add to specific paragraphpara = doc.add_paragraph()run = para.add_run()run.add_picture('logo.png', width=Inches(1.5))

Formatting

Paragraph Formatting

python

from docx.enum.text import WD_ALIGN_PARAGRAPHfrom docx.shared import Pt, Inches
para = doc.add_paragraph('Formatted text')para.alignment = WD_ALIGN_PARAGRAPH.CENTERpara.paragraph_format.line_spacing = 1.5para.paragraph_format.space_after = Pt(12)para.paragraph_format.first_line_indent = Inches(0.5)

from docx.enum.text import WD_ALIGN_PARAGRAPHfrom docx.shared import Pt, Inches
para = doc.add_paragraph('Formatted text')para.alignment = WD_ALIGN_PARAGRAPH.CENTERpara.paragraph_format.line_spacing = 1.5para.paragraph_format.space_after = Pt(12)para.paragraph_format.first_line_indent = Inches(0.5)

Character Formatting

python

run = para.add_run('Styled text')run.bold = Truerun.italic = Truerun.underline = Truerun.font.name = 'Arial'run.font.size = Pt(14)run.font.color.rgb = RGBColor(0x00, 0x00, 0xFF)  # Blue

run = para.add_run('Styled text')run.bold = Truerun.italic = Truerun.underline = Truerun.font.name = 'Arial'run.font.size = Pt(14)run.font.color.rgb = RGBColor(0x00, 0x00, 0xFF)  # Blue

Page Setup

python

from docx.enum.section import WD_ORIENTfrom docx.shared import Inches
section = doc.sections[0]section.page_width = Inches(11)section.page_height = Inches(8.5)section.orientation = WD_ORIENT.LANDSCAPEsection.left_margin = Inches(1)section.right_margin = Inches(1)

from docx.enum.section import WD_ORIENTfrom docx.shared import Inches
section = doc.sections[0]section.page_width = Inches(11)section.page_height = Inches(8.5)section.orientation = WD_ORIENT.LANDSCAPEsection.left_margin = Inches(1)section.right_margin = Inches(1)

Headers & Footers

python

section = doc.sections[0]
# Headerheader = section.headerheader.paragraphs[0].text = "Company Name"header.paragraphs[0].alignment = WD_ALIGN_PARAGRAPH.CENTER
# Footer with page numbersfooter = section.footerpara = footer.paragraphs[0]para.text = "Page "# Add page number fieldrun = para.add_run()fldChar1 = OxmlElement('w:fldChar')fldChar1.set(qn('w:fldCharType'), 'begin')run._r.append(fldChar1)# ... (field code for page number)

section = doc.sections[0]
# Headerheader = section.headerheader.paragraphs[0].text = "Company Name"header.paragraphs[0].alignment = WD_ALIGN_PARAGRAPH.CENTER
# Footer with page numbersfooter = section.footerpara = footer.paragraphs[0]para.text = "Page "# Add page number fieldrun = para.add_run()fldChar1 = OxmlElement('w:fldChar')fldChar1.set(qn('w:fldCharType'), 'begin')run._r.append(fldChar1)# ... (field code for page number)

Styles

python

# Use built-in stylesdoc.add_paragraph('Heading', style='Heading 1')doc.add_paragraph('Quote', style='Quote')doc.add_paragraph('List item', style='List Bullet')
# Common styles:# - 'Normal', 'Heading 1-9', 'Title', 'Subtitle'# - 'Quote', 'Intense Quote', 'List Bullet', 'List Number'# - 'Table Grid', 'Light Shading', 'Medium Grid 1'

# Use built-in stylesdoc.add_paragraph('Heading', style='Heading 1')doc.add_paragraph('Quote', style='Quote')doc.add_paragraph('List item', style='List Bullet')
# Common styles:# - 'Normal', 'Heading 1-9', 'Title', 'Subtitle'# - 'Quote', 'Intense Quote', 'List Bullet', 'List Number'# - 'Table Grid', 'Light Shading', 'Medium Grid 1'

Best Practices

Structure First: Plan document hierarchy before coding
Use Styles: Consistent formatting via styles, not manual formatting
Save Often: Call doc.save() periodically for large documents
Handle Errors: Check file existence before opening
Clean Up: Remove template placeholders after filling

Common Patterns

Report Template

python

def create_report(title, sections):    doc = Document()    doc.add_heading(title, 0)    doc.add_paragraph(f'Generated: {datetime.now()}')        for section_title, content in sections.items():        doc.add_heading(section_title, 1)        doc.add_paragraph(content)        return doc

def create_report(title, sections):    doc = Document()    doc.add_heading(title, 0)    doc.add_paragraph(f'Generated: {datetime.now()}')        for section_title, content in sections.items():        doc.add_heading(section_title, 1)        doc.add_paragraph(content)        return doc

Table from Data

python

def add_data_table(doc, headers, rows):    table = doc.add_table(rows=1, cols=len(headers))    table.style = 'Table Grid'        # Headers    for i, header in enumerate(headers):        table.rows[0].cells[i].text = header        table.rows[0].cells[i].paragraphs[0].runs[0].bold = True        # Data rows    for row_data in rows:        row = table.add_row()        for i, value in enumerate(row_data):            row.cells[i].text = str(value)        return table

def add_data_table(doc, headers, rows):    table = doc.add_table(rows=1, cols=len(headers))    table.style = 'Table Grid'        # Headers    for i, header in enumerate(headers):        table.rows[0].cells[i].text = header        table.rows[0].cells[i].paragraphs[0].runs[0].bold = True        # Data rows    for row_data in rows:        row = table.add_row()        for i, value in enumerate(row_data):            row.cells[i].text = str(value)        return table

Mail Merge Pattern

python

def fill_template(template_path, replacements):    doc = Document(template_path)        for para in doc.paragraphs:        for key, value in replacements.items():            if f'{{{key}}}' in para.text:                para.text = para.text.replace(f'{{{key}}}', value)        return doc

def fill_template(template_path, replacements):    doc = Document(template_path)        for para in doc.paragraphs:        for key, value in replacements.items():            if f'{{{key}}}' in para.text:                para.text = para.text.replace(f'{{{key}}}', value)        return doc

Examples

Example 1: Create a Business Letter

python

from docx import Documentfrom docx.shared import Inches, Ptfrom docx.enum.text import WD_ALIGN_PARAGRAPHfrom datetime import datetime
doc = Document()
# Letterheaddoc.add_paragraph('ACME Corporation')doc.add_paragraph('123 Business Ave, Suite 100')doc.add_paragraph('New York, NY 10001')doc.add_paragraph()
# Datedoc.add_paragraph(datetime.now().strftime('%B %d, %Y'))doc.add_paragraph()
# Recipientdoc.add_paragraph('Mr. John Smith')doc.add_paragraph('XYZ Company')doc.add_paragraph('456 Industry Blvd')doc.add_paragraph('Chicago, IL 60601')doc.add_paragraph()
# Salutationdoc.add_paragraph('Dear Mr. Smith,')doc.add_paragraph()
# Bodybody = """We are pleased to inform you that your proposal has been accepted...
[Letter body continues...]
Thank you for your continued partnership."""
for para_text in body.split('\n\n'):    doc.add_paragraph(para_text)
doc.add_paragraph()doc.add_paragraph('Sincerely,')doc.add_paragraph()doc.add_paragraph()doc.add_paragraph('Jane Doe')doc.add_paragraph('CEO, ACME Corporation')
doc.save('business_letter.docx')

from docx import Documentfrom docx.shared import Inches, Ptfrom docx.enum.text import WD_ALIGN_PARAGRAPHfrom datetime import datetime
doc = Document()
# Letterheaddoc.add_paragraph('ACME Corporation')doc.add_paragraph('123 Business Ave, Suite 100')doc.add_paragraph('New York, NY 10001')doc.add_paragraph()
# Datedoc.add_paragraph(datetime.now().strftime('%B %d, %Y'))doc.add_paragraph()
# Recipientdoc.add_paragraph('Mr. John Smith')doc.add_paragraph('XYZ Company')doc.add_paragraph('456 Industry Blvd')doc.add_paragraph('Chicago, IL 60601')doc.add_paragraph()
# Salutationdoc.add_paragraph('Dear Mr. Smith,')doc.add_paragraph()
# Bodybody = """We are pleased to inform you that your proposal has been accepted...
[Letter body continues...]
Thank you for your continued partnership."""
for para_text in body.split('\n\n'):    doc.add_paragraph(para_text)
doc.add_paragraph()doc.add_paragraph('Sincerely,')doc.add_paragraph()doc.add_paragraph()doc.add_paragraph('Jane Doe')doc.add_paragraph('CEO, ACME Corporation')
doc.save('business_letter.docx')

Example 2: Create a Report with Table

python

from docx import Documentfrom docx.shared import Inches
doc = Document()doc.add_heading('Q4 Sales Report', 0)
# Executive Summarydoc.add_heading('Executive Summary', 1)doc.add_paragraph('Q4 2024 showed strong growth across all regions...')
# Sales Tabledoc.add_heading('Regional Performance', 1)
table = doc.add_table(rows=1, cols=4)table.style = 'Medium Grid 1 Accent 1'
headers = ['Region', 'Q3 Sales', 'Q4 Sales', 'Growth']for i, header in enumerate(headers):    table.rows[0].cells[i].text = header
data = [    ['North America', '$1.2M', '$1.5M', '+25%'],    ['Europe', '$800K', '$950K', '+18%'],    ['Asia Pacific', '$600K', '$750K', '+25%'],]
for row_data in data:    row = table.add_row()    for i, value in enumerate(row_data):        row.cells[i].text = value
doc.save('sales_report.docx')

from docx import Documentfrom docx.shared import Inches
doc = Document()doc.add_heading('Q4 Sales Report', 0)
# Executive Summarydoc.add_heading('Executive Summary', 1)doc.add_paragraph('Q4 2024 showed strong growth across all regions...')
# Sales Tabledoc.add_heading('Regional Performance', 1)
table = doc.add_table(rows=1, cols=4)table.style = 'Medium Grid 1 Accent 1'
headers = ['Region', 'Q3 Sales', 'Q4 Sales', 'Growth']for i, header in enumerate(headers):    table.rows[0].cells[i].text = header
data = [    ['North America', '$1.2M', '$1.5M', '+25%'],    ['Europe', '$800K', '$950K', '+18%'],    ['Asia Pacific', '$600K', '$750K', '+25%'],]
for row_data in data:    row = table.add_row()    for i, value in enumerate(row_data):        row.cells[i].text = value
doc.save('sales_report.docx')

Limitations

Cannot execute macros or VBA code
Complex templates may lose some formatting
Limited support for advanced features (SmartArt, Charts)
No direct PDF conversion (use separate tool)
Track changes reading is limited

Installation

Resources

Source and attribution

Source:claude-office-skills/skillsindocx-manipulationat commit9c4c7d5

License: MIT

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal

Docx Manipulation

DOCX Manipulation Skill

Overview

How to Use

Domain Knowledge

python-docx Fundamentals

Document Structure

Adding Content

Paragraphs & Headings

Tables

Images

Formatting

Paragraph Formatting

Character Formatting

Page Setup

Headers & Footers

Styles

Best Practices

Common Patterns

Report Template

Table from Data

Mail Merge Pattern

Examples

Example 1: Create a Business Letter

Example 2: Create a Report with Table

Limitations

Installation

Resources

Source and attribution

More from claude-office-skills/skills

Whatsapp Automation

Xlsx Manipulation

Web Search

Weekly Report

Tiktok Marketing

Template Engine

More in Documents & Office

Pdf

View Pdf

Wiki Ado Convert

Esign Field Placement

Visa Doc Translate

Google Workspace Ops